14.5.9.8.6 Pooling in Convolutional Neural Networks Implementations

Chapter Contents (Back)
CNN. Pooling.

He, K.M.[Kai-Ming], Zhang, X.Y.[Xiang-Yu], Ren, S.Q.[Shao-Qing], Sun, J.[Jian],
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition,
PAMI(37), No. 9, September 2015, pp. 1904-1916.
IEEE DOI 1508
BibRef
Earlier: ECCV14(III: 346-361).
Springer DOI 1408
Accuracy BibRef

He, K.M.[Kai-Ming], Zhang, X.Y.[Xiang-Yu], Ren, S.Q.[Shao-Qing], Sun, J.[Jian],
Deep Residual Learning for Image Recognition,
CVPR16(770-778)
IEEE DOI 1612
Award, CVPR. BibRef
And:
Identity Mappings in Deep Residual Networks,
ECCV16(IV: 630-645).
Springer DOI 1611
BibRef

Lee, C.Y.[Chen-Yu], Gallagher, P.[Patrick], Tu, Z.W.[Zhuo-Wen],
Generalizing Pooling Functions in CNNs: Mixed, Gated, and Tree,
PAMI(40), No. 4, April 2018, pp. 863-875.
IEEE DOI 1804
computational complexity, feedforward neural nets, learning (artificial intelligence), neural net architecture, supervised classification BibRef

Xu, C.Y.[Chun-Yan], Yang, J.[Jian], Lai, H.J.[Han-Jiang], Gao, J.B.[Jun-Bin], Shen, L.L.[Lin-Lin], Yan, S.C.[Shui-Cheng],
UP-CNN: Un-pooling augmented convolutional neural network,
PRL(119), 2019, pp. 34-40.
Elsevier DOI 1902
Convolutional neural network, Cross-layer interaction, Ratio un-pooling, Image classification BibRef

Lai, X.[Xin], Zhou, L.[Le], Fu, Z.[Zeyu], Naqvi, S.M.[Syed Mohsen], Chambers, J.[Jonathon],
Enhanced pooling method for convolutional neural networks based on optimal search theory,
IET-IPR(13), No. 12, October 2019, pp. 2152-2161.
DOI Link 1911
BibRef

Yu, R.X.[Rui-Xuan], Sun, J.[Jian], Li, H.B.[Hui-Bin],
Second-Order Spectral Transform Block for 3D Shape Classification and Retrieval,
IP(29), 2020, pp. 4530-4543.
IEEE DOI 2003
3D shape analysis, second-order pooling, spectral transform, shape representation BibRef

Wang, S.D.[Shi-Dong], Guan, Y.[Yu], Shao, L.[Ling],
Multi-Granularity Canonical Appearance Pooling for Remote Sensing Scene Classification,
IP(29), 2020, pp. 5396-5407.
IEEE DOI 2004
Granular feature representation, transformation invariant, Gaussian Covariance matrix, remote sensing scene classification BibRef

Singh, P.[Pravendra], Raj, P.[Prem], Namboodiri, V.P.[Vinay P.],
EDS pooling layer,
IVC(98), 2020, pp. 103923.
Elsevier DOI 2006
Feature pooling layer, Convolutional neural network, Deep learning, Object recognition BibRef

Xiao, B.[Bo], Li, X.Y.[Xiang-Yu], Li, C.G.[Chun-Guang], Xu, Q.F.[Qian-Fang],
A novel Pooling Block for improving lightweight deep neural networks,
PRL(135), 2020, pp. 307-312.
Elsevier DOI 2006
Deep learning, Image classification, Object detection, Pooling block, Lightweight neural networks BibRef

Akodad, S.[Sara], Bombrun, L.[Lionel], Xia, J.[Junshi], Berthoumieu, Y.[Yannick], Germain, C.[Christian],
Ensemble Learning Approaches Based on Covariance Pooling of CNN Features for High Resolution Remote Sensing Scene Classification,
RS(12), No. 20, 2020, pp. xx-yy.
DOI Link 2010
BibRef

Zhu, X.G.[Xiao-Guang], Wang, H.Y.[Hao-Yu], Liu, P.L.[Pei-Lin], Yang, Z.T.[Zhan-Tao], Qian, J.C.[Jiu-Chao],
Graph-based reasoning attention pooling with curriculum design for content-based image retrieval,
IVC(115), 2021, pp. 104289.
Elsevier DOI 2110
Content-based image retrieval, Graph convolutional networks, Curriculum design BibRef

Gao, H.Y.[Hong-Yang], Liu, Y.[Yi], Ji, S.W.[Shui-Wang],
Topology-Aware Graph Pooling Networks,
PAMI(43), No. 12, December 2021, pp. 4512-4518.
IEEE DOI 2112
Network topology, Natural language processing, Diversity reception, Training data, Sampling methods, graph topology BibRef

Gao, Z.T.[Zi-Teng], Wang, L.M.[Li-Min], Wu, G.S.[Gang-Shan],
LIP: Local Importance-Based Pooling,
IJCV(131), No. 1, January 2023, pp. 363-384.
Springer DOI 2301
BibRef
Earlier: ICCV19(3354-3363)
IEEE DOI 2004
convolutional neural nets, image classification, importance sampling, learning (artificial intelligence), Neural networks BibRef

Xu, S.[Sixiang], Muselet, D.[Damien], Trémeau, A.[Alain], Jiao, L.C.[Li-Cheng],
Improved Bilinear Pooling With Pseudo Square-Rooted Matrix,
SPLetters(30), 2023, pp. 423-427.
IEEE DOI 2305
Feature extraction, Symmetric matrices, Matrix decomposition, Image classification, Convolutional neural networks, Newton iterations BibRef

Bayraktar, E.[Ertugrul], Yigit, C.B.[Cihat Bora],
Conditional-pooling for improved data transmission,
PR(145), 2024, pp. 109978.
Elsevier DOI Code:
WWW Link. 2311
Pooling, Data sampling, Noise reduction, Feature selection BibRef


Shibata, T.[Takashi], Tanaka, M.[Masayuki], Okutomi, M.[Masatoshi],
Robustizing Object Detection Networks Using Augmented Feature Pooling,
ACCV22(V:89-106).
Springer DOI 2307
BibRef

Chen, F.[Fang], Datta, G.[Gourav], Kundu, S.[Souvik], Beerel, P.A.[Peter A.],
Self-Attentive Pooling for Efficient Deep Learning,
WACV23(3963-3972)
IEEE DOI 2302
Deep learning, Limiting, Memory management, Feature extraction, System-on-chip, Image restoration, Embedded sensing/real-time techniques BibRef

Liu, Y.[Yue], Cui, L.X.[Li-Xin], Wang, Y.[Yue], Bai, L.[Lu],
ABDPool: Attention-based Differentiable Pooling,
ICPR22(3021-3026)
IEEE DOI 2212
Aggregates, Benchmark testing, Graph neural networks, Task analysis, Standards BibRef

Akodad, S.[Sara], Bombrun, L.[Lionel], Puscasu, M.[Maria], Xia, J.[Junshi], Germain, C.[Christian], Berthoumieu, Y.[Yannick],
Deep Ensemble Learning Model Based on Covariance Pooling of Multi-Layer CNN Features,
ICIP22(1081-1085)
IEEE DOI 2211
Image recognition, Image analysis, Neural networks, Convolutional neural networks, Remote sensing, Standards, CNN BibRef

Chen, J.J.[Jia-Jing], Kakillioglu, B.[Burak], Ren, H.T.[Huan-Tao], Velipasalar, S.[Senem],
Why Discard if You can Recycle?: A Recycling Max Pooling Module for 3D Point Cloud Analysis,
CVPR22(549-557)
IEEE DOI 2210
Point cloud compression, Representation learning, Solid modeling, Semantics, Network architecture BibRef

He, Y.J.[Yang-Ji], Liang, W.H.[Wei-Han], Zhao, D.Y.[Dong-Yang], Zhou, H.Y.[Hong-Yu], Ge, W.F.[Wei-Feng], Yu, Y.Z.[Yi-Zhou], Zhang, W.Q.[Wen-Qiang],
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning,
CVPR22(9109-9119)
IEEE DOI 2210
Visualization, Semantics, Self-supervised learning, Benchmark testing, Transformers, Feature extraction, retrieval BibRef

Stergiou, A.[Alexandros], Poppe, R.[Ronald], Kalliatakis, G.[Grigorios],
Refining activation downsampling with SoftPool,
ICCV21(10337-10346)
IEEE DOI 2203
Training, Image recognition, Refining, Memory management, Object detection, Minimization, Feature extraction, Recognition and classification BibRef

Chen, J.C.[Jia-Cheng], Hu, H.X.[He-Xiang], Wu, H.[Hao], Jiang, Y.N.[Yu-Ning], Wang, C.H.[Chang-Hu],
Learning the Best Pooling Strategy for Visual Semantic Embedding,
CVPR21(15784-15793)
IEEE DOI 2111
Adaptation models, Visualization, Computational modeling, Semantics, Benchmark testing, Feature extraction, Data models BibRef

Hssayni, E.H., Ettaouil, M.,
A Novel Pooling Method for Regularization of Deep Neural networks,
ISCV20(1-6)
IEEE DOI 2011
convolutional neural nets, image classification, learning (artificial intelligence), pattern classification, Spectral Dropout. BibRef

Douillard, A.[Arthur], Cord, M.[Matthieu], Ollion, C.[Charles], Robert, T.[Thomas], Valle, E.[Eduardo],
Podnet: Pooled Outputs Distillation for Small-tasks Incremental Learning,
ECCV20(XX:86-102).
Springer DOI 2011
BibRef

Chen, Z., Zhang, J., Ding, R., Marculescu, D.,
ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection,
WACV20(1169-1178)
IEEE DOI 2006
Convolution, Task analysis, Object detection, Interpolation, Acceleration, Redundancy, Computational modeling BibRef

Kobayashi, T.[Takumi],
Global Feature Guided Local Pooling,
ICCV19(3364-3373)
IEEE DOI 2004
convolutional neural nets, feature extraction, image classification, learning (artificial intelligence), Probabilistic logic BibRef

Wan, W., Chen, J., Li, T., Huang, Y., Tian, J., Yu, C., Xue, Y.,
Information Entropy Based Feature Pooling for Convolutional Neural Networks,
ICCV19(3404-3413)
IEEE DOI 2004
convolutional neural nets, entropy, feature extraction, image classification, image segmentation, Training BibRef

Huang, J., Li, Z., Li, N., Liu, S., Li, G.,
AttPool: Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention Mechanism,
ICCV19(6479-6488)
IEEE DOI 2004
convolutional neural nets, feature extraction, graph theory, learning (artificial intelligence), pattern classification, Adaptation models BibRef

Gao, Z.L.[Zi-Lin], Xie, J.T.[Jiang-Tao], Wang, Q.L.[Qi-Long], Li, P.H.[Pei-Hua],
Global Second-Order Pooling Convolutional Networks,
CVPR19(3019-3028).
IEEE DOI 2002
BibRef

Xu, Y., Nakayama, H.,
DCT Based Information-Preserving Pooling for Deep Neural Networks,
ICIP19(894-898)
IEEE DOI 1910
Deep neural network, information preservation, spectral pooling, 2D-DCT BibRef

Hu, G., Dixit, C., Luong, D., Gao, Q., Cheng, L.,
Salience Guided Pooling in Deep Convolutional Networks,
ICIP19(360-364)
IEEE DOI 1910
Pooling, Salience feature, Classification, Edge BibRef

Saeedan, F.[Faraz], Weber, N.[Nicolas], Goesele, M.[Michael], Roth, S.[Stefan],
Detail-Preserving Pooling in Deep Networks,
CVPR18(9108-9116)
IEEE DOI 1812
Standards, Visualization, Convolutional neural networks, Task analysis, Feature extraction, Distortion, Adaptive systems BibRef

Ferrŕ, A.[Aina], Aguilar, E.[Eduardo], Radeva, P.[Petia],
Multiple Wavelet Pooling for CNNs,
WiCV-E18(IV:671-675).
Springer DOI 1905
BibRef

Ryu, J.B.[Jong-Bin], Yang, M.H.[Ming-Hsuan], Lim, J.W.[Jong-Woo],
DFT-based Transformation Invariant Pooling Layer for Visual Classification,
ECCV18(XIV: 89-104).
Springer DOI 1810
DFT magnitude pooling replaces the traditional max/average pooling layer between the convolution and fully-connected layers. BibRef

Yu, K.C.[Kai-Cheng], Salzmann, M.[Mathieu],
Statistically-Motivated Second-Order Pooling,
ECCV18(VII: 621-637).
Springer DOI 1810
Second-order network. BibRef

Simon, M.[Marcel], Gao, Y.[Yang], Darrell, T.J.[Trevor J.], Denzler, J.[Joachim], Rodner, E.[Erik],
Generalized Orderless Pooling Performs Implicit Salient Matching,
ICCV17(4970-4979)
IEEE DOI 1802
CNN. Learn the pooling strategy also. feature extraction, feedforward neural nets, image classification, image matching, image representation, Visualization BibRef

Zhai, S.F.[Shuang-Fei], Wu, H.[Hui], Kumar, A.[Abhishek], Cheng, Y.[Yu], Lu, Y.X.[Yong-Xi], Zhang, Z.F.[Zhong-Fei], Feris, R.S.[Rogerio S.],
S3Pool: Pooling with Stochastic Spatial Sampling,
CVPR17(4003-4011)
IEEE DOI 1711
Convolution, Distortion, Feature extraction, Neural networks, Standards, Stochastic, processes BibRef

Cui, Y., Zhou, F., Wang, J., Liu, X., Lin, Y., Belongie, S.J.[Serge J.],
Kernel Pooling for Convolutional Neural Networks,
CVPR17(3049-3058)
IEEE DOI 1711
Kernel, Neural networks, Taylor series, Tensile stress, Training, Visualization BibRef

Li, P.H.[Pei-Hua], Xie, J.T.[Jiang-Tao], Wang, Q.L.[Qi-Long], Gao, Z.L.[Zi-Lin],
Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization,
CVPR18(947-955)
IEEE DOI 1812
Covariance matrices, Graphics processing units, Training, Matrix decomposition, Backpropagation, Symmetric matrices, Computer architecture BibRef

Chen, Z.Q.[Zi-Qian], Lin, J.[Jie], Chandrasekhar, V.[Vijay], Duan, L.Y.[Ling-Yu],
Gated Square-Root Pooling for Image Instance Retrieval,
ICIP18(1982-1986)
IEEE DOI 1809
Logic gates, Principal component analysis, Training, Benchmark testing, Image retrieval, Task analysis, Learning to gate BibRef

Xie, L.X.[Ling-Xi], Tian, Q.[Qi], Flynn, J.[John], Wang, J.D.[Jing-Dong], Yuille, A.L.[Alan L.],
Geometric Neural Phrase Pooling: Modeling the Spatial Co-Occurrence of Neurons,
ECCV16(I: 645-661).
Springer DOI 1611
BibRef

Bell, S.[Sean], Zitnick, C.L.[C. Lawrence], Bala, K.[Kavita], Girshick, R.[Ross],
Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks,
CVPR16(2874-2883)
IEEE DOI 1612
BibRef

Yang, F., Choi, W., Lin, Y.,
Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers,
CVPR16(2129-2137)
IEEE DOI 1612
BibRef

Mopuri, K.R.[Konda Reddy], Babu, R.V.[R. Venkatesh],
Object level deep feature pooling for compact image representation,
DeepLearn15(62-70)
IEEE DOI 1510
Computational modeling BibRef

Yang, M.[Mu], Li, B.[Brian], Fan, H.Q.[Hao-Qiang], Jiang, Y.N.[Yu-Ning],
Randomized spatial pooling in deep convolutional networks for scene recognition,
ICIP15(402-406)
IEEE DOI 1512
deep convolutional networks BibRef

Yoo, D.G.[Dong-Geun], Park, S.G.[Sung-Gyun], Lee, J.Y.[Joon-Young], Kweon, I.S.[In So],
Multi-scale pyramid pooling for deep convolutional representation,
DeepLearn15(71-80)
IEEE DOI 1510
Accuracy BibRef

Liu, L.Q.[Ling-Qiao], Shen, C.H.[Chun-Hua], van den Hengel, A.J.[Anton J.],
The treasure beneath convolutional layers: Cross-convolutional-layer pooling for image classification,
CVPR15(4749-4757)
IEEE DOI 1510
DCNN. BibRef

Gong, Y.C.[Yun-Chao], Wang, L.W.[Li-Wei], Guo, R.Q.[Rui-Qi], Lazebnik, S.[Svetlana],
Multi-scale Orderless Pooling of Deep Convolutional Activation Features,
ECCV14(VII: 392-407).
Springer DOI 1408
Deep convolutional neural networks BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Efficient Implementations Convolutional Neural Networks .


Last update:Nov 26, 2024 at 16:40:19